A hand gesture recognition method for an intelligent smart home TV remote control system

스마트 홈에서의 TV 제어 시스템을 위한 손 제스처 인식 방법

  • Kim, Dae-Hwan (IM Lab, Dept. of Computer Science & Engineering POSTECH) ;
  • Cho, Sang-Ho (IM Lab, Dept. of Computer Science & Engineering POSTECH) ;
  • Cheon, Young-Jae (IM Lab, Dept. of Computer Science & Engineering POSTECH) ;
  • Kim, Dai-Jin (IM Lab, Dept. of Computer Science & Engineering POSTECH)
  • 김대환 (포항공과대학교 컴퓨터공학과 지능형미디어 연구실) ;
  • 조상호 (포항공과대학교 컴퓨터공학과 지능형미디어 연구실) ;
  • 천영재 (포항공과대학교 컴퓨터공학과 지능형미디어 연구실) ;
  • 김대진 (포항공과대학교 컴퓨터공학과 지능형미디어 연구실)
  • Published : 2007.10.26

Abstract

This paper presents a intuitive, simple and easy smart home TV remote control system using the hand gesture recognition. Hand candidate regions are detected by cascading policy of the part of human anatomy on the disparity map image, Exact hand region is extracted by the graph-cuts algorithm using the skin color information. Hand postures are represented by shape features which are extracted by a simple shape extraction method. We use the forward spotting accumulative HMMs for a smart home TV remote control system. Experimental results show that the proposed system has a good recognition rate of 97.33 % for TV remote control in real-time.

Keywords